Optimize date_part Minute by avoiding unnecessary computation #14043
Description
Is your feature request related to a problem or challenge?
Open an issue to track the status of this optimization
Related
#13449
apache/arrow-rs#6746
Describe the solution you'd like
I guess there are some changes in arrow-rs left to do.
Describe alternatives you've considered
No response
Additional context
impl ExtractDatePartExt for PrimitiveArray<TimestampSecondType> {
fn date_part(&self, part: DatePart) -> Result<Int32Array, ArrowError> {
// TimestampSecond only encodes number of seconds, so these will always be 0
let array =
if let DatePart::Millisecond | DatePart::Microsecond | DatePart::Nanosecond = part {
Int32Array::new(vec![0; self.len()].into(), self.nulls().cloned())
} else if let Some(tz) = get_tz(self.data_type())? {
let map_func = get_date_time_part_extract_fn(part);
self.unary_opt(|d| {
timestamp_s_to_datetime(d)
.map(|c| Utc.from_utc_datetime(&c).with_timezone(&tz))
.map(map_func)
})
} else {
let map_func = get_date_time_part_extract_fn(part);
self.unary_opt(|d| timestamp_s_to_datetime(d).map(map_func))
};
Ok(array)
}
}If I remember correctly, we need to switch timestamp_s_to_datetime to timestamp_s_to_time and extract the data from Minute